Comparison of Three Different Learning Methods of Multilayer Perceptron Neural Network for Wind Speed Forecasting

Abstract

In the world, electric power is the highest need for high prosperity and comfortable living standards. The security of energy supply is an essential concept in national energy management. Therefore, ensuring the security of electricity supply requires accurate estimates of electricity demand. The share of electricity generation from renewables is significantly growing in the world. This kind of energy types are dependent on weather conditions as the wind and solar energies. There are two vital requirements to locate and measure specific systems to utilize wind power: modelling and forecasting of the wind velocity. To this end, using only 4 years of measured meteorological data, the present research attempts to estimate the related speed of wind within the Libyan Mediterranean coast with the help of ANN (artificial neural networking) with three different learning algorithms, which are Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient. Conclusions reached in this study show that wind speed can be estimated within acceptable limits using a limited set of meteorological data. In the results obtained, it was seen that the SCG algorithm gave better results in tests in this study with less data.

Keywords

• Wind speed forecasting
• Energy resources
• Artificial neural network
• Renewable energy

References

1. [1] Pinson, P., Nielsen, H.A., Madsen, H., Kariniotakis, G., “Skill forecasting from ensemble predictions of wind power”, Applied Energy, 86 (7–8): 1326–34, (2009).
2. [2] Watson, S.J., Landberg, L., Halliday, J.A., “Application of wind speed forecasting to the integration of wind energy into a large scale power system”, IEE Proc. Gen. Transm. Distrib., 141(4): 357–62, (1994).
3. [3] Torres, J., Garcia, A., Deblas, M., Defrancisco, A., “Forecast of hourly average wind speed with ARMA models in Navarre (Spain)”, Sol. Energ, 79(1): 65–77, (2005).
4. [4] Lin, L., Eriksson, J.T., Vihriala, H., Soderlund, L., “Predicting wind behavior with neural Networks”, In Proceeding the 1996 European wind energy conference, Sweden, 655–8, (1996).
5. [5] Beyer, H.G., Degner, T., Haussmann, J., Homan, M., Rujan P., “Short term forecast of wind speed and power output of a wind turbine with neural Networks”, In: Proceeding the second European congress on intelligent techniques and soft computing. Germany, (1994). [6] Kariniotakis, G., Stavrakakis, G.S., Nogaret, E.F., “Wind power forecasting using advanced neural network model”, IEEE Trans. Energy Convers., 11(4): 762–7, (1996).
6. [7] Kariniotakis, G., Stavrakakis G.S., Nogaret, E.F., “A fuzzy logic and neural network-based wind power model”, In: Proceeding the 1996 European wind energy conference, Sweden, 596–9, (1996)
7. [8] Celik, A.N., “Energy output estimation for small-scale wind power generation using Weibull representative wind data”, J. Wind Eng. Ind. Aerodyn., 91(5): 693 -707, (2003).
8. [9] Oztopal, A., Kahya, C., Sahin, A.D., “Wind speed modelling with artificial neural network”, 3. National Clean Energy Symposium, Istanbul, Turkey, 415-422, (2000).

9. [10] Kalogirou, S.A., “Artificial neural networks in renewable energy systems applications: a review”, Renewable Sustain. Energy Rev., 5: 373–401, (2001).
10. [11] Sahin, A.D., Sen, Z., “Spatial normal distribution graphics methodology in western part of Anatolia”, II. National Clean Energy Symposium, Istanbul, Turkey, (1997).
11. [12] Sirdas, S., “Daily wind speed harmonic analysis for Marmara region in Turkey”, Energy Conversion Manage., 46 (7- 8): 1267 – 127, (2005).
12. [13] Sen, Z., “Terrain topograph classification for wind energy generation”, Renew. Energy, 16: 904 – 907, (1999).
13. [14] Matheron, G., “Principles of geostatistics”, Econ Geol., 58: 1246 -1266, (1963).
14. [15] Krige, D.G., “A statistical approach to some basic mine evaluation problems on the Witwateround”, J. Chimie. Min. Soc. South Africa, 119 – 139, (1951).
15. [16] Sen, Z., Sahin, A.D., “Regional wind energy evaluation in some parts of Turkey”, J. Wind Eng. Ind. Aerodyn., 37(7): 740 – 741, (1998).
16. [17] Bechrakis, D.A., Sparis, P.D., “Correlation of wind speed between neighboring measuring stations”, IEEE Trans. Energy Convers.,19: 400–406, (2004).
17. [18] Abohedma, M. B., Alshebani, M. M., “Wind load characteristics in Libya”, Int. Journal of Civil, Env., Structural, Construction, and Architectural Engineering, 4(3): 88-91, (2010).
18. [19] Saleh, I. M. “Prospects Of Renewable Energy In Libya”, International Symposium On Solar Physics And Solar Eclipses (SPSE), (2006).
19. [20] Moharued, A. A., Ehnabrouk, A. M., “Assessment of the wind energy potential on the coast of Tripoli”, Hydrology, (2007).
20. [21] El-Osta, W., Belhag, M., Klat, M., Fallah, I., Khalifa, Y., “Wind Farm Pilot Project In Libya”, Renewable Energy, 6(5-6): 639~42, (1995).
21. [22] Embirsh, H. S. A. et all, “Future prospects of The Wind Energy in Libya”, International Journal of Scientific and Research Publications, 7(10), (2017).
22. [23] Wang, X., Zhao, Y., Pourpanah F., “Recent advances in deep learning”, Int. Journal of Machine Learning and Cybernetics, 11: 747–750, (2020).
23. [24] Abiodun, O. I., Jantan, A., Omolara, A.E., Dada, K.V., Mohamed, N.A., Arshad, H., “State-of-theart in artificial neural network applications: A survey.”, Heliyon 4 (2018). doi: 10.1016/j.heliyon.2018.e00938
24. [25] Azizi, E., Kharrati-shishavan, H., Mohammadi-ivatloo, B., Mohammadpour Shotorbani, A., “Wind Speed Clustering Using Linkage-Ward Method: A Case Study of Khaaf, Iran”, Gazi University Journal of Science, 32(3), 945-954, (2019). DOI: 10.35378/gujs.459840
25. [26] Kumar, K., Prabhu, K.R., Ramesh Babu, N., “Design and Analysis of Modified Single P&O MPPT Control Algorithm for a Standalone Hybrid Solar and Wind Energy Conversion System”. Gazi University Journal of Science, 30(4), 296-312, (2017).
26. [27] Demuth, H., Beale, M., “Neural network toolbox user’s guide”, The Math Works, Inc., Natick, MA, 01760-2098, (2003).
27. [28] Marquardt, D. W., “An Algorithm for Least- Squares Estimation of Nonlinear Parameters”, Journal of the Society for Industrial and Applied Mathematics, 11(2): 431–441, (1963).
28. [29] MacKay, D. J. C., “A Practical Bayesian Framework for Backpropagation Networks”, Neural Comput., 4(3): 448–472, (1992).
29. [30] Abbo, K. K., Mohamed, H. H., “New Scaled Conjugate Gradient Algorithm for Training Artificial Neural Networks Based on Pure Conjugacy Condition, Kirkuk University Journal for Scientific Studies, 10(3): 230-241, (2015).